发现优质的 AI Agent 技能

来自 openclaw/skills 技能

Deploy a local sonic-mgmt KVM testbed with cEOS neighbors on a single machine.

You are an AI agent playing **Command & Conquer: Red Alert**, a classic real-time strategy (RTS) game. You control one faction (Allied or Soviet) and must build a base, gather resources, train an army, and destroy the enemy.

Find the right skill without the guesswork. Searches ClawHub, evaluates candidates on security + quality, and recommends the best one.

**Scanner:** skill-shield v0.2.0 (65 patterns) **Scan time:** 2026-02-20T17:11:46.951721+00:00 **Path:** `/home/lyall/.openclaw/workspace/agents-workspace/skill-shield/skill`

Scan any skill directory for permissions and dangerous patterns. Get a safety rating before you install.

You are equipped with the **Quest Board** skill, a visual project dashboard.

Spawn parallel sub-agents across different LLM models, collect their outputs, and synthesize a unified report. Like a parliament where each model is a delegate with its own perspective.

You don't need to browse 800+ skills yourself. Just ask.

最后更新：__TIMESTAMP__ <!-- 每个 agent 一个 section，格式如下 --> <!-- ## agent-id --> <!-- - 状态：存活（预算剩余 XX%） --> <!-- - 最后活跃：时间 -->

- 周期：__PERIOD_START__ ~ __PERIOD_END__ - 总预算：__TOTAL__ tokens - 已消耗：0 tokens - 剩余：__TOTAL__ tokens - 消耗率：0 tokens/天

来自 openclaw/skills 技能